Positive Technology Journal - artificial_intelligence_robotics

Miruko Eyeball Robotic Eye

noreply@blogspirit.com (Andrea Gaggioli) — Fri, 25 Sep 2009 18:31:35 +0200

Miruko is a camera robot in the shape of an eyeball capable of tracking objects and faces. Worn on the player’s sleeve, Miruko’s roving eye scans the surroundings in search of virtual monsters that are invisible to the naked human eye. When a virtual monster is spotted, the mechanical eyeball rolls around in its socket and fixes its gaze on the monster’s location. By following Miruko’s line of sight, the player is able to locate the virtual monster and “capture” it via his or her iPhone camera.

In this video, Miruko’s creators demonstrate how the robotic eyeball can be used as an interface for a virtual monster-hunting game played in a real-world environment.

According to its creators, Miruko can be used for augmented reality games, security, and navigation.

HAL: New assistive walking device

noreply@blogspirit.com (Andrea Gaggioli) — Mon, 21 Sep 2009 17:10:00 +0200

Japanese company Cyberdyne, with the scientific support provided by Professor Sankai of Tsukuba University, have developed the Hybrid Assistive Limb - HAL - a device designed to help people walk or carry heavy loads. The assistive walking system weights 10 kilogram and has a battery at the back. Embedded sensors collects electric signals that are delivered to the brain through the skin surface. Thanks to these sensors, the system can help users to move in the direction they are thinking. The walking speed is 1.8 km p/h.

Watch the HAL in action in this video:

Robot butler

noreply@blogspirit.com (Andrea Gaggioli) — Tue, 22 Jul 2008 14:25:00 +0200

From Smart Mobs

(Credit: Fraunhofer IPA)

German researchers from the Fraunhofer Institute have introduced their third generation of household robots, the Care-O-Bot 3. The robot has has a flexible arm with seven degrees of freedom and a hand with three fingers. This allows it to pick up bottles, cups and similar objects and to operate machines.

Here are the major functionalities of Care-O-bot 3:

Omnidirectional Navigation: Care-O-bot 3 has an omnidirectional platform, with four steered and driven wheels. This kinematic system enables the robot to move in any desired direction and therefore also safely to negotiate narrow passages.
Safe Manipulation: Care-O-bot 3 is equipped with a highly flexible, commercial arm with seven degrees of freedom as well as with a three-finger hand. This makes it capable of gripping and operating a large number of different everyday objects.
3D Environment Detection: A multiplicity of sensors enables Care-O-bot 3 to detect the environment in which it is operating. These range from stereo vision colour cameras and laser scanners to a 3D depth-image camera.
Software Architecture/Middleware: Several interlinked computers are used to evaluate and control the sensors and actuators inside the robot. The system resources are coordinated and managed by a specially developed middleware which controls communications between the individual processes and which reacts appropriately in the event of a malfunction.
Human-Machine Interaction: The primary interface between Care-Obot 3 and the user consists of a tray attached to the front of the robot, which carries objects for exchange between the human and the robot. The tray includes a touch screen and retracts automatically when not in use. A laser projector on the gripper also enables the robot to project information onto objects.

A second life for AI

noreply@blogspirit.com (Andrea Gaggioli) — Sun, 16 Mar 2008 23:46:06 +0100

Source: Eetimes

Passing the Turing test - the holy grail of AI (a human conversing with a computer can't tell it's not human) - may now be possible in a limited way with the world's fastest supercomputer (IBM's Blue Gene) and mimicking the behavior of a human-controlled avatar in a virtual world, according to AI experts at Rensselaer Polytechnic Institute. "We are building a knowledge base that corresponds to all of the relevant background for our synthetic character--where he went to school, what his family is like, and so on," said Selmer Bringsjord, head of Rensselaer's Cognitive Science Department and leader of the research project. The researchers plan to engineer, from the start, a full-blown intelligent character and converse with him in an interactive virtual environment, like Second Life.

read full article here

Avatar-controlled robots

noreply@blogspirit.com (Andrea Gaggioli) — Wed, 19 Dec 2007 23:53:41 +0100

Via KurzweilAI.net

Researchers at Korea Advanced Institute of Science and Technology have developed a system for controlling physical robots using software robots, displayed as virtual-reality avatars.

Article

Toyota unveils robot violinist

noreply@blogspirit.com (Andrea Gaggioli) — Fri, 07 Dec 2007 14:03:46 +0100

Via Pink Tentacle

Link

Video

Simroid

noreply@blogspirit.com (Andrea Gaggioli) — Tue, 04 Dec 2007 08:37:47 +0100

Via Pink Tentacle

Simroid is a robotic dental patient designed by Kokoro Company Ltd as a training tool for dentists.

The simulated patient can follow spoken instructions, closely monitor a dentist’s performance during mock treatments, and react in a human-like way to mouth pain thanks to mouth sensors.

video

Brain2Robot

noreply@blogspirit.com (Andrea Gaggioli) — Sun, 25 Nov 2007 23:50:00 +0100

Researchers at the Fraunhofer Institute for Computer Architecture and Software Technology FIRST and the Charite hospital in Berlin have developed a new EEG-controlled robot arm, which might one day bring help to people with paralysis.

Electrodes attached to the patient's scalp measure the brain's electrical signals, which are amplified and transmitted to a computer. Highly efficient algorithms analyze these signals using a self-learning technique. The software is capable of detecting changes in brain activity that take place even before a movement is carried out. It can recognize and distinguish between the patterns of signals that correspond to an intention to raise the left or right hand, and extract them from the pulses being fired by millions of other neurons in the brain. These neural signal patterns are then converted into control instructions for the computer. "The aim of the project is to help people with severe motor disabilities to carry out everyday tasks. The advantage of our technology is that it is capable of translating an intended action directly into instructions for the computer," says team leader Florin Popescu. The Brain2Robot project has been granted around 1.3 million euros in research funding under the EU's sixth Framework Programme (FP6). Its focus lies on developing medical applications, in particular control systems for prosthetics, personal robots and wheelchairs. The researchers have also developed a "thought-controlled typewriter", a communication device that enables severely paralyzed patients to pick out letters of the alphabet and write texts. The robot arm could be ready for commercialization in just a few years' time.

Press release:Brain2Robot

Project page:Brain2Robot

Japanese android recognizes and uses body language

noreply@blogspirit.com (Andrea Gaggioli) — Thu, 25 Oct 2007 22:45:00 +0200

Via Pink Tentacle

Japan’s National Institute of Information and Communications Technology (NICT) researchers have developed an autonomous humanoid robot that can recognize and use body language. According to the press release, the android can use nonverbal communication skills such as gestures and touch to facilitate natural interaction with humans. NICT researchers envision future applications of this technology in robots that can work in the home or assist with rescue operations when disaster strikes.

NICT press release (japanese)

NIPS 2007 WORKSHOP: Robotics Challenges for Machine Learning

noreply@blogspirit.com (Andrea Gaggioli) — Sun, 07 Oct 2007 22:12:46 +0200

Via Neurobot

Dates: 7-8 December, 2007

Organizers:
Jan Peters (Max Planck Institute for Biological Cybernetics & USC), Marc Toussaint (Technical University of Berlin)

http://www.robot-learning.de
email: nips07@robot-learning.de

Abstract Submission Deadline: October 21, 2007
Acceptance Notification: October 26, 2007